Hugging Face's logo

Aharneish
/
gpt2-sailit

Text Generation
Transformers
PyTorch
TensorBoard
Safetensors
gpt2
text-generation-inference
Inference Endpoints
Model card Files Metrics Community
1
gpt2-sailit
File size: 2,415 Bytes 
7a0a26a
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
 
{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 2.3876404494382024,
  "global_step": 8500,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.14,
      "learning_rate": 9.719101123595506e-06,
      "loss": 3.6724,
      "step": 500
    },
    {
      "epoch": 0.28,
      "learning_rate": 9.438202247191012e-06,
      "loss": 3.4748,
      "step": 1000
    },
    {
      "epoch": 0.42,
      "learning_rate": 9.157303370786517e-06,
      "loss": 3.4067,
      "step": 1500
    },
    {
      "epoch": 0.56,
      "learning_rate": 8.876404494382023e-06,
      "loss": 3.3562,
      "step": 2000
    },
    {
      "epoch": 0.7,
      "learning_rate": 8.595505617977528e-06,
      "loss": 3.3173,
      "step": 2500
    },
    {
      "epoch": 0.84,
      "learning_rate": 8.314606741573035e-06,
      "loss": 3.2991,
      "step": 3000
    },
    {
      "epoch": 0.98,
      "learning_rate": 8.033707865168539e-06,
      "loss": 3.2694,
      "step": 3500
    },
    {
      "epoch": 1.12,
      "learning_rate": 7.752808988764046e-06,
      "loss": 3.2269,
      "step": 4000
    },
    {
      "epoch": 1.26,
      "learning_rate": 7.471910112359552e-06,
      "loss": 3.2163,
      "step": 4500
    },
    {
      "epoch": 1.4,
      "learning_rate": 7.191011235955056e-06,
      "loss": 3.1938,
      "step": 5000
    },
    {
      "epoch": 1.54,
      "learning_rate": 6.910112359550563e-06,
      "loss": 3.192,
      "step": 5500
    },
    {
      "epoch": 1.69,
      "learning_rate": 6.629213483146067e-06,
      "loss": 3.1795,
      "step": 6000
    },
    {
      "epoch": 1.83,
      "learning_rate": 6.348314606741574e-06,
      "loss": 3.166,
      "step": 6500
    },
    {
      "epoch": 1.97,
      "learning_rate": 6.06741573033708e-06,
      "loss": 3.1556,
      "step": 7000
    },
    {
      "epoch": 2.11,
      "learning_rate": 5.786516853932585e-06,
      "loss": 3.1371,
      "step": 7500
    },
    {
      "epoch": 2.25,
      "learning_rate": 5.50561797752809e-06,
      "loss": 3.1231,
      "step": 8000
    },
    {
      "epoch": 2.39,
      "learning_rate": 5.224719101123596e-06,
      "loss": 3.1135,
      "step": 8500
    }
  ],
  "max_steps": 17800,
  "num_train_epochs": 5,
  "total_flos": 8883145211904000.0,
  "trial_name": null,
  "trial_params": null
}